© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11525
    Prev
    Next
    INDEX
    Explanations

    physical quantities and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataReader
    0.43
    Czas
    0.41
     همین
    0.39
    ฌ
    0.39
     کیوں
    0.38
     vậy
    0.38
     یہی
    0.38
    Dichloro
    0.38
     hilfre
    0.38
    मिस्ट्री
    0.37
    POSITIVE LOGITS
     desired
    0.52
     P
    0.47
     Amount
    0.46
    wanted
    0.45
     wanted
    0.44
    ță
    0.44
    ́
    0.43
     WANTED
    0.42
    ̀n
    0.42
     Money
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.